Claude Code v2.1.85 Release: MCP Improvements, Hook Filters, and Bug Fixes

Claude Code v2.1.85 is a maintenance release focused on improving MCP (Model Context Protocol) functionality, adding granular control over hooks, and fixing numerous bugs across the system.

New Features and Improvements

MCP Enhancements:

• Added CLAUDE_CODE_MCP_SERVER_NAME and CLAUDE_CODE_MCP_SERVER_URL environment variables to MCP headersHelper scripts, allowing one helper to serve multiple servers
• MCP OAuth now follows RFC 9728 Protected Resource Metadata discovery to find the authorization server
• Fixed MCP step-up authorization failing when a refresh token exists — servers requesting elevated scopes via 403 insufficient_scope now correctly trigger the re-authorization flow
• Fixed Python Agent SDK: type:'sdk' MCP servers passed via --mcp-config are no longer dropped during startup

Hook System Improvements:

• Added conditional if field for hooks using permission rule syntax (e.g., Bash(git *)) to filter when they run, reducing process spawning overhead
• PreToolUse hooks can now satisfy AskUserQuestion by returning updatedInput alongside permissionDecision: "allow", enabling headless integrations that collect answers via their own UI
• Fixed --worktree exiting with an error in non-git repositories before the WorktreeCreate hook could run

Other Additions:

• Added timestamp markers in transcripts when scheduled tasks (/loop, CronCreate) fire
• Added trailing space after [Image #N] placeholder when pasting images
• Deep link queries (claude-cli://open?q=…) now support up to 5,000 characters, with a "scroll to review" warning for long pre-filled prompts
• Plugins blocked by organization policy (managed-settings.json) can no longer be installed or enabled, and are hidden from marketplace views
• tool_parameters in OpenTelemetry tool_result events are now gated behind OTEL_LOG_TOOL_DETAILS=1

Bug Fixes

Core Functionality:

• Fixed /compact failing with "context exceeded" when the conversation has grown too large for the compact request itself to fit
• Fixed /plugin enable and /plugin disable failing when a plugin's install location differs from where it's declared in settings
• Fixed deniedMcpServers setting not blocking claude.ai MCP servers
• Fixed switch_display in the computer-use tool returning "not available in this session" on multi-monitor setups
• Fixed crash when OTEL_LOGS_EXPORTER, OTEL_METRICS_EXPORTER, or OTEL_TRACES_EXPORTER is set to none
• Fixed diff syntax highlighting not working in non-native builds

Performance and Memory:

• Fixed memory leak in remote sessions when a streaming response is interrupted
• Fixed persistent ECONNRESET errors during edge connection churn by using a fresh TCP connection on retry
• Improved @-mention file autocomplete performance on large repositories
• Improved scroll performance with large transcripts by replacing WASM yoga-layout with a pure TypeScript implementation
• Reduced UI stutter when compaction triggers on large sessions

User Interface and Terminal:

• Fixed prompts getting stuck in the queue after running certain slash commands, with up-arrow unable to retrieve them
• Fixed raw key sequences appearing in the prompt when running over SSH or in the VS Code integrated terminal
• Fixed Remote Control session status staying stuck on "Requires Action" after a permission is resolved
• Fixed shift+enter and meta+enter being intercepted by typeahead suggestions instead of inserting newlines
• Fixed stale content bleeding through when scrolling up during streaming
• Fixed terminal left in enhanced keyboard mode after exit in Ghostty, Kitty, WezTerm, and other terminals supporting the Kitty keyboard protocol — Ctrl+C and Ctrl+D now work correctly after quitting
• Improved PowerShell dangerous command detection

This release is primarily for developers using Claude Code with MCP integrations, custom hooks, or experiencing specific bugs in previous versions.